Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 914 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.5685. Min Act: -0.0000

Data Index: 519764 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.3221. Min Act: -0.0000

Data Index: 825084 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.4056. Min Act: 0.0000

Data Index: 410616 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2975. Min Act: -0.0000

Data Index: 281228 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2576. Min Act: -0.0000

Data Index: 882533 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2424. Min Act: -0.0000

Data Index: 290127 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.2001. Min Act: -0.0000

Data Index: 85053 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1999. Min Act: -0.0000

Data Index: 608583 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1216. Min Act: -0.0000

Data Index: 178817 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1137. Min Act: -0.0000

Data Index: 21807 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1717. Min Act: -0.0000

Data Index: 363041 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1123. Min Act: -0.0000

Data Index: 77758 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1297. Min Act: -0.0000

Data Index: 751730 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1024. Min Act: -0.0000

Data Index: 787508 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.0939. Min Act: -0.0000

Data Index: 52028 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.0880. Min Act: -0.0000

Data Index: 907030 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1032. Min Act: -0.0000

Data Index: 375109 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.0751. Min Act: -0.0000

Data Index: 283353 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.0271. Min Act: -0.0000

Data Index: 264767 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.5685. Min Range: -1.5685

Max Act: 1.1267. Min Act: -0.0000

Data Index: 383662 (C4 (Web Text))

Max Activating Token Index: 844